Evaluating Machine Learning Methods of Analyzing Multiclass Metabolomics

Multiclass metabolomic studies have become popular for revealing the differences in multiple stages of complex diseases, various lifestyles, or the effects of specific treatments. In multiclass metabolomics, there are multiple data manipulation steps for analyzing raw data, which consist of data filtering, the imputation of missing values, data normalization, marker identification, sample separation, classification, and so on. In each step, several to dozens of machine learning methods can be chosen for the given data set, with potentially hundreds or thousands of method combinations in the whole data processing chain. Therefore, a clear understanding of these machine learning methods is helpful for selecting an appropriate method combination for obtaining stable and reliable analytical results of specific data. However, there has rarely been an overall introduction or evaluation of these methods based on multiclass metabolomic data. Herein, detailed descriptions of these machine learning methods in multiple data manipulation steps are reviewed. Moreover, an assessment of these methods was performed using a benchmark data set for multiclass metabolomics. First, 12 imputation methods for imputing missing values were evaluated based on the PSS (Procrustes statistical shape analysis) and NRMSE (normalized root-mean-square error) values. Second, 17 normalization methods for processing multiclass metabolomic data were evaluated by applying the PMAD (pooled median absolute deviation) value. Third, different methods of identifying markers of multiclass metabolomics were evaluated based on the CWrel (relative weighted consistency) value. Fourth, nine classification methods for constructing multiclass models were assessed using the AUC (area under the curve) value. Performance evaluations of machine learning methods are highly recommended to select the most appropriate method combination before performing the final analysis of the given data. Overall, detailed descriptions and evaluation of various machine learning methods are expected to improve analyses of multiclass metabolomic data.

Iron toxicity-induced physiological and metabolite profile variations among tolerant and sensitive rice varieties

Iron toxicity stress causes physiological and metabolic changes in rice and other plants. To date, there is little information about the metabolite profile of rice under Fe toxicity conditions. In fact, metabolite has a contribution to the physiological condition of plants. Plant metabolomics is a study of low-molecular weight metabolites in plants under certain conditions. The objective of the research was to investigate physiological and metabolic changes in rice under Fe toxicity stress. Two-week-old seedlings of four rice varieties with various Fe toxicity tolerance levels were stressed hydroponically with 400 ppm FeSO4.7H2O for 10 d. Numerous physiological characters were observed and untargeted metabolomic analysis was carried out using gas chromatography-mass spectrophotometry (GC-MS). The results showed Fe toxicity induced physiological and metabolite variation in rice. By comparing the metabolites synthesized in Fe toxicity-stressed plants with control plants, it showed that elaidic acid, linoleic acid, and linolenic acid could be as metabolite marker candidates for rice response to Fe toxicity stress. When plants exposed to Fe toxicity stress, elaidic acid increased, whereas linoleic- and linolenic acid decreased. The alteration of fatty acid composition in the root and shoot suggests the alteration of metabolites is one of the tolerance strategies of rice to Fe toxicity stress. This finding offers an insight about the tolerance strategies of rice under Fe toxicity stress related to the maintenance process of the cell membranes during this stress. The genes underlying biosynthesis of the fatty acid could be a target of future research on responsible genes for Fe toxicity tolerance in rice.